Mulam Harikrishna, Mudigonda Malini
Department of Electronics and Instrumentation Engineering, VNR Vignana Jyothi Institute of Engineering and Technology, Vignana Jyothi Nagar, Nizampet Rd, Pragathi Nagar, Hyderabad, Telangana 500090, India.
Department of Biomedical Engieering, University College of Engineering, Osmania University, Osmania University Main Rd, Amberpet, Hyderabad, Telangana 500007, India.
Biomed Tech (Berl). 2020 Jan 28;65(1):11-22. doi: 10.1515/bmt-2018-0109.
In recent times, the control of human-computer interface (HCI) systems is triggered by electrooculography (EOG) signals. Eye movements recognized based on the EOG signal pattern are utilized to govern the HCI system and do a specific job based on the type of eye movement. With the knowledge of various related examinations, this paper intends a novel model for eye movement recognition based on EOG signals by utilizing Grey Wolf Optimization (GWO) with neural network (NN). Here, the GWO is used to minimize the error function from the classifier. The performance of the proposed methodology was investigated by comparing the developed model with conventional methods. The results reveal the loftier performance of the adopted method with the error minimization analysis and recognition performance analysis in correspondence with varied performance measures such as accuracy, sensitivity, specificity, precision, false-positive rate (FPR), false-negative rate (FNR), negative predictive value (NPV), false discovery rate (FDR) and the F1 score.
近年来，人机接口（HCI）系统的控制由眼电图（EOG）信号触发。基于EOG信号模式识别的眼球运动被用于控制HCI系统，并根据眼球运动的类型执行特定任务。基于各种相关研究，本文旨在通过结合灰狼优化算法（GWO）和神经网络（NN），提出一种基于EOG信号的眼球运动识别新模型。在此，GWO用于最小化分类器的误差函数。通过将所开发的模型与传统方法进行比较，研究了所提出方法的性能。结果表明，所采用的方法在误差最小化分析和识别性能分析方面具有更高的性能，与各种性能指标（如准确率、灵敏度、特异性、精度、误报率（FPR）、漏报率（FNR）、阴性预测值（NPV）、错误发现率（FDR）和F1分数）相对应。
